Machine Learning


WS 2020





V3 + Ü1 (6 ECTS credits)
Note: This page is for a course from a previous semester.
Find a list of current courses on the Teaching page.


Due to the ongoing COVID-19 pandemic, the lectures and tutorials will be conducted in an online format via Zoom for the Winter Semester 2020/21. For each lecture/tutorial session, the meeting link will be conveyed to you in advance via Moodle. If you plan on taking this course, please register for it via RWTHOnline since doing so will automatically add you to the Moodle learning room for this course and give you access to all course-related content (this includes recordings of the online lectures). The exam will most likely still be conducted in a physical/written format, but due to the rapidly changing pandemic-related regulations, this cannot be ascertained at this point in time.

For newly enrolled students unable to arrive in Germany: It has come to our knowledge that there are several newly enrolled students whose visa processes have been delayed due to the pandemic. As of now, we do not have a mechanism for conducting the exam in an online format, so that will not be possible. However, we would like to clarify that it is possible to attend the course now (i.e., take part in lectures and tutorials), and give the exam next year (in the Winter semester 2021/22).

Please use the Moodle forum for all course-related queries.

Lecture Description

The goal of Machine Learning is to develop techniques that enable a machine to "learn" how to perform certain tasks from experience.

The important part here is the learning from experience. That is, we do not try to encode the knowledge ourselves, but the machine should learn it itself from training data. The tools for this are statistical learning and probabilistic inference techniques. Such techniques are used in many real-world applications. This lecture will teach the fundamental machine learning know-how that underlies such capabilities. In addition, we show current research developments and how they are applied to solve real-world tasks.

Example questions that could be addressed with the techniques from the lecture include

  • Is this email important or spam?
  • What is the likelihood that this credit card transaction is fraudulent?
  • Does this image contain a face?


The class is accompanied by exercises that will allow you to collect hands-on experience with the algorithms introduced in the lecture.

There will be both pen&paper exercises and practical programming exercises (roughly 1 exercise sheet every 2 weeks). Please submit your solutions electronically through the RWTH Moodle system.

We ask you to work in teams of 2-3 students.


The first half of the lecture will follow the book by Bishop. For the second half, we will use the Deep Learning book by Goodfellow as a reference.

  • Christopher M. Bishop, Pattern Recognition and Machine Learning, Springer, 2006
  • Ian Goodfellow, Yoshua Bengio, Aaron Courville, Deep Learning, MIT Press, 2016

Wherever research papers are necessary for a deeper understanding, we will make them available in RWTH Moodle.

Additional Resources

  • Kevin Murphy, Machine Learning -- A Probabilistic Perspective, MIT Press, 2012.

Python Resources

Disclaimer Home Visual Computing institute RWTH Aachen University